Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 953 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5727. Min Act: -0.0002

Data Index: 1005454 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1599351 (Python Code)

Max Activating Token Index: 270

Text #2

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5198. Min Act: -0.0002

Data Index: 1177016 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4566. Min Act: -0.0002

Data Index: 1214214 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1598151 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1383194 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4736. Min Act: -0.0002

Data Index: 257880 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4871. Min Act: -0.0002

Data Index: 904608 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4861. Min Act: -0.0001

Data Index: 690365 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4676. Min Act: -0.0001

Data Index: 1153401 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1444209 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4600. Min Act: -0.0001

Data Index: 316645 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1399484 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4584. Min Act: -0.0002

Data Index: 380337 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4578. Min Act: -0.0002

Data Index: 1231944 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4352. Min Act: -0.0002

Data Index: 626314 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4715. Min Act: -0.0001

Data Index: 1315689 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4430. Min Act: -0.0002

Data Index: 1419142 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1549796 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.5727. Min Range: -0.5727

Max Act: 0.4414. Min Act: -0.0001

Data Index: 1512943 (Python Code)

Max Activating Token Index: 624